Hysocs/Aozora_Trainer

Low VRAM SDXL Fine-Tuning Toolkit 2026: Train Full-Quality AI Models on 12GB GPUs

The 2026 VRAM-Smart Fine-Tuning Suite for SDXL and ANIMA on 12GB GPUs

Optimized ai-toolkit fork without local training data

Dead simple FLUX LoRA training UI with LOW VRAM support

The most efficient one-page LoRA trainer for Anima 2B. Optimized for 6GB+ VRAM, featuring a smart dataset analyzer and real-time previews.

Train LoRAs for Qwen-Image 2.1, FLUX.2 Klein 9B, FLUX.3 Image Klein, Krea 2, Z-Image, MOSS-Image, ERNIE-Image, Ideogram 4, Anima, SDXL (Pony, Illustrious, NoobAI), LTX 2.3, MiniMax-H3, and more on NVIDIA GPUs from 4–8 GB VRAM. One install, one launcher, NF4 models. Windows, Linux and RunPod.

Scalable and memory-optimized training of diffusion models

Low-VRAM LoRA Training for Krea-2

WeeLLM runs large diffusion models with as little as 4 GB of VRAM, without any quantization. It dynamically determines how many layers can fit within the available VRAM and streams the text encoder and transformer layers to the GPU layer by layer, enabling inference on hardware with limited VRAM. It supports both safetensors and GGUF models.